search

camenduru / stable-diffusion-webui-colab

stable diffusion webui colab
The Unlicense
15.45k stars 2.6k forks source link

[Bug]: Tiled Diffusion & VAE can not work #476

Closed kzai8108 closed 9 months ago

kzai8108 commented 10 months ago

What happened?

The problem occurred after the update. No matter if any parameters are changed, it cannot be used normally.

Colab cell output

Noise Inversion:   0% 0/50 [00:00<?, ?it/s]*** Error completing request
*** Arguments: ('task(2h2gbxlmcd6qxt9)', 0, '(simple background, white background:1.4), (masterpiece, top quality, best quality, official art:1.2), (8k, highest detailed:1.4), an (anime Nendoroid:1.4) of 1 girl, (figurine, sculpture, chibi:1.4), (thigh high stockings:1.3), (white clothes:1.4) + blue clothes, (fighting action:1.2), <lora:add_detail:0.3>', '(bad-hands-5, bad-artist:1.2), (out of frame:1.2), easy negative, worst quality, low quality, monochrome, grayscales, (6 more fingers on one hand, extra fingers, fused fingers, mutated hands, poorly drawn hands:1.4), (deformity, bad legs, error legs, bad feet, malformed limbs, extra limbs, mutation, bad anatomy, cloned face, disfigured, poorly drawn feet, poorly drawn face:1.2), skin spots, acnes, skin blemishes, age spot, ugly, mutilated, watermark, text', [], <PIL.Image.Image image mode=RGBA size=512x768 at 0x7A9F8E7D1360>, None, None, None, None, None, None, 30, 16, 4, 0, 1, False, False, 1, 1, 9.5, 1.5, 0.5, -1.0, -1.0, 0, 0, 0, False, 0, 768, 512, 1, 0, 0, 32, 0, '', '', '', [], 0, False, True, False, 0, -1, True, 'MultiDiffusion', False, True, 1024, 1024, 96, 96, 48, 8, '4x-UltraSharp', 4, True, 50, 1, 1, 64, False, False, False, False, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, True, 2048, 128, True, True, False, False, False, '', 0, False, False, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, None, 'Refresh models', <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x7a9f80bf2530>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x7a9f8ed54790>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x7a9f8e6005b0>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x7a9f80bf3af0>, False, '1:1,1:2,1:2', '0:0,0:0,0:1', '0.2,0.8,0.8', 150, 0.2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, '<ul>\n<li><code>CFG Scale</code> should be 2 or lower.</li>\n</ul>\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 0.5, 'Linear', 'None', '<p style="margin-bottom:0.75em">Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8</p>', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, 'positive', 'comma', 0, False, False, '', '', '<p style="margin-bottom:0.75em">Will upscale the image by the selected scale factor; use width and height sliders to set tile size</p>', 64, 0, 2, 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, None, None, False, None, None, False, None, None, False, None, None, False, 50) {}
    Traceback (most recent call last):
      File "/content/stable-diffusion-webui/modules/call_queue.py", line 55, in f
        res = list(func(*args, **kwargs))
      File "/content/stable-diffusion-webui/modules/call_queue.py", line 35, in f
        res = func(*args, **kwargs)
      File "/content/stable-diffusion-webui/modules/img2img.py", line 198, in img2img
        processed = process_images(p)
      File "/content/stable-diffusion-webui/modules/processing.py", line 620, in process_images
        res = process_images_inner(p)
      File "/content/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/batch_hijack.py", line 42, in processing_process_images_hijack
        return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
      File "/content/stable-diffusion-webui/modules/processing.py", line 739, in process_images_inner
        samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
      File "/content/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/hook.py", line 451, in process_sample
        return process.sample_before_CN_hack(*args, **kwargs)
      File "/content/stable-diffusion-webui/modules/processing.py", line 1316, in sample
        samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_utils/utils.py", line 243, in wrapper
        return fn(*args, **kwargs)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_utils/utils.py", line 243, in wrapper
        return fn(*args, **kwargs)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/abstractdiffusion.py", line 605, in sample_img2img
        latent = self.find_noise_for_image_sigma_adjustment(sampler.model_wrap, self.noise_inverse_steps, prompts)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_utils/utils.py", line 243, in wrapper
        return fn(*args, **kwargs)
      File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
        return func(*args, **kwargs)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/abstractdiffusion.py", line 677, in find_noise_for_image_sigma_adjustment
        eps = self.get_noise(x_in * c_in, t, cond_in, steps - i)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 290, in get_noise
        return self.sample_one_step(x_in, org_func, repeat_func, custom_func)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 183, in sample_one_step
        x_tile_out = repeat_func(x_tile, bboxes)
      File "/content/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 276, in repeat_func
        x_tile_out = shared.sd_model.apply_model(x_tile, sigma_in_tile, cond=new_cond)
      File "/content/stable-diffusion-webui/modules/sd_hijack_utils.py", line 17, in <lambda>
        setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
      File "/content/stable-diffusion-webui/modules/sd_hijack_utils.py", line 28, in __call__
        return self.__orig_func(*args, **kwargs)
      File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 858, in apply_model
        x_recon = self.model(x_noisy, t, **cond)
      File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "/content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 1335, in forward
        out = self.diffusion_model(x, t, context=cc)
      File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "/content/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/hook.py", line 853, in forward_webui
        raise e
      File "/content/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/hook.py", line 850, in forward_webui
        return forward(*args, **kwargs)
      File "/content/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/hook.py", line 591, in forward
        control = param.control_model(x=x_in, hint=hint, timesteps=timesteps, context=context, y=y)
      File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "/content/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/cldm.py", line 31, in forward
        return self.control_model(*args, **kwargs)
      File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "/content/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/cldm.py", line 311, in forward
        h += guided_hint
    RuntimeError: The size of tensor a (96) must match the size of tensor b (256) at non-singleton dimension 3

Which colab and model(s) were you using when the error occurred?

anything_5_webui_colab

Which Public WebUI Colab URL were you using when the error occurred?

remote.moe

If you used HiRes mode when the error occurred, please provide the Hires info

No response